© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 16148
    Prev
    Next
    INDEX
    Explanations

    elements related to data structures and operations in programming, particularly within the context of data analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.75
     HasFactory
    -0.72
     препратки
    -0.67
    gameserver
    -0.64
    SourceChecksum
    -0.63
    +#+
    -0.60
     couvercle
    -0.59
    permitAll
    -0.59
     Roskov
    -0.58
     bezeichneter
    -0.57
    POSITIVE LOGITS
    df
    1.31
    dd
    1.13
     df
    1.13
    DF
    1.05
    DD
    0.93
    dt
    0.90
     dd
    0.89
    DT
    0.88
    dc
    0.87
    DS
    0.85
    Activations Density 0.308%

    No Known Activations